Optimising manufacturing efficiency: a data analytics solution for machine utilisation and production insights

This paper proposes a non-invasive, data-driven methodology for monitoring and optimising machine utilisation in manufacturing environments. By analysing high-resolution power consumption data, the system automatically classifies machine states (off, idling, and working, and segments operational periods into discrete production events. Unsupervised learning techniques enable the identification of production patterns, product typologies, and anomalies, supporting improvements in operational efficiency and quality control. The approach also estimates energy consumption and cost using time-of-use tariffs, offering insights into both performance and sustainability. Experimental evaluations across multiple industrial settings demonstrate the method’s robustness, with high agreement with production records and significant potential for reducing idle time, improving scheduling, and enhancing resource allocation. This work presents a scalable and interpretable analytics framework to support data-driven decision-making in modern manufacturing operations.